Question

因此，在我之前的问题[在此处找到] [1]中，我尝试解析我已经设法使用@ SiHa帮助下载的JSON文件。 JSON的结构如下：

{"properties": [{"property": "name", "value": "A random company name"}, {"property": "companyId", "value": 123456789}]}{"properties": [{"property": "name", "value": "Another random company name"}, {"property": "companyId", "value": 31415999}]}{"properties": [{"property": "name", "value": "Yet another random company"}, {"property": "companyId", "value": 10101010}]}

我已经通过稍微修改@ SiHa的代码来获得这个代码：

def get_companies():
            create_get_recent_companies_call = "https://api.hubapi.com/companies/v2/companies/?hapikey={hapikey}".format(hapikey=wta_hubspot_api_key)
            headers = {'content-type': 'application/json'}
            create_get_recent_companies_response = requests.get(create_get_recent_companies_call, headers=headers)
            if create_get_recent_companies_response.status_code == 200:
                while True:
                    for i in create_get_recent_companies_response.json()[u'companies']:

                        all_the_companies = { "properties": [
                                                    { "property": "name", "value": i[u'properties'][u'name'][u'value'] },
                                                    { "property": "companyId", "value": i[u'companyId'] }
                                                ]
                                            }

                        with open("all_the_companies.json", "a") as myfile:
                            myfile.write(json.dumps(all_the_companies))
                        #print(companyProperties)
                    offset = create_get_recent_companies_response.json()[u'offset']
                    hasMore = create_get_recent_companies_response.json()[u'has-more']
                    if not hasMore:
                        break
                    else:
                        create_get_recent_companies_call = "https://api.hubapi.com/companies/v2/companies/?hapikey={hapikey}&offset={offset}".format(hapikey=wta_hubspot_api_key, offset=offset)
                        create_get_recent_companies_response = requests.get(create_get_recent_companies_call, headers=headers)


            else:
                print("Something went wrong, check the supplied field values.\n")
                print(json.dumps(create_get_recent_companies_response.json(), sort_keys=True, indent=4))

这是第一部分。现在，我尝试使用以下代码提取两件事：1）name和2 {} companyId。

#!/usr/bin/python
# -*- coding: utf-8 -*-

import sys
import os.path
import requests
import json
import csv
import glob2
import shutil
import time
import time as howLong
from time import sleep
from time import gmtime, strftime

# Local Testing Version
findCSV = glob2.glob('*contact*.csv')

theDate = time=strftime("%Y-%m-%d", gmtime())
theTime = time=strftime("%H:%M:%S", gmtime())

# Exception handling
try:
    testData = findCSV[0]
except IndexError:
    print ("\nSyncronisation attempted on {date} at {time}: There are no \"contact\" CSVs, please upload one and try again.\n").format(date=theDate, time=theTime)
    print("====================================================================================================================\n")
    sys.exit()

for theCSV in findCSV:

    def process_companies():
        with open('all_the_companies.json') as data_file:
            data = json.load(data_file)
            for i in data:
                company_name = data[i][u'name']
                #print(company_name)
                if row[0].lower() == company_name.lower():
                    contact_company_id = data[i][u'companyId']
                    #print(contact_company_id)
                    return contact_company_id

                else:
                    print("Something went wrong, check the \"get_companies()\" function.\n")
                    print(json.dumps(create_get_recent_companies_response.json(), sort_keys=True, indent=4))

    if __name__ == "__main__":
        start_time = howLong.time()
        process_companies()
        print("This operation took %s seconds.\n" % (howLong.time() - start_time))
        sys.exit()

不幸的是，它不起作用 - 我得到了以下追溯：

Traceback (most recent call last):
  File "wta_parse_json.py", line 62, in <module>
    process_companies()
  File "wta_parse_json.py", line 47, in process_companies
    data = json.load(data_file)
  File "/System/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/json/__init__.py", line 290, in load
    **kw)
  File "/System/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/json/__init__.py", line 338, in loads
    return _default_decoder.decode(s)
  File "/System/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/json/decoder.py", line 369, in decode
    raise ValueError(errmsg("Extra data", s, end, len(s)))
ValueError: Extra data: line 1 column 130 - line 1 column 1455831 (char 129 - 1455830)

我确保我使用json.dumps而不是json.dump来打开该文件，但仍无效。：（

我现在放弃了JSON，并尝试使用以下代码导出一个简单的CSV：

    def get_companies():
            create_get_recent_companies_call = "https://api.hubapi.com/companies/v2/companies/?hapikey={hapikey}".format(hapikey=wta_hubspot_api_key)
            headers = {'content-type': 'application/json'}
            create_get_recent_companies_response = requests.get(create_get_recent_companies_call, headers=headers)
            if create_get_recent_companies_response.status_code == 200:
                while True:
                    for i in create_get_recent_companies_response.json()[u'companies']:

                        all_the_companies = "{name},{id}\n".format(name=i[u'properties'][u'name'][u'value'], id=i[u'companyId'])
                        all_the_companies.encode('utf-8')

                        with open("all_the_companies.csv", "a") as myfile:
                            myfile.write(all_the_companies)
                        #print(companyProperties)
                    offset = create_get_recent_companies_response.json()[u'offset']
                    hasMore = create_get_recent_companies_response.json()[u'has-more']
                    if not hasMore:
                        break
                    else:
                        create_get_recent_companies_call = "https://api.hubapi.com/companies/v2/companies/?hapikey={hapikey}&offset={offset}".format(hapikey=wta_hubspot_api_key, offset=offset)
                        create_get_recent_companies_response = requests.get(create_get_recent_companies_call, headers=headers)
  [1]: http://stackoverflow.com/questions/36148346/unable-to-loop-through-paged-api-responses-with-python

但看起来这似乎也不对 - 即使我已经阅读了格式问题，并添加了.encode('utf-8')个添加内容。我仍然得到以下追溯：

Traceback (most recent call last):
  File "wta_get_companies.py", line 78, in <module>
    get_companies()
  File "wta_get_companies.py", line 57, in get_companies
    all_the_companies = "{name},{id}\n".format(name=i[u'properties'][u'name'][u'value'], id=i[u'companyId'])
UnicodeEncodeError: 'ascii' codec can't encode character u'\ufffd' in position 3: ordinal not in range(128)

Answer 1

JSON数据一个接一个地有三个对象;简化为：

{ .. }{ .. }{ .. }

这不是JSON标准所支持的。 Python应如何解析它？自动将其包装在一个数组中？将它分配给三个不同的变量？只需使用第一个？

你可能想把它包装成一个数组，简化：

[{ .. },{ .. },{ .. }]

或完整：

[{"properties": [{"property": "name", "value": "A random company name"}, {"property": "companyId", "value": 123456789}]},{"properties": [{"property": "name", "value": "Another random company name"}, {"property": "companyId", "value": 31415999}]},{"properties": [{"property": "name", "value": "Yet another random company"}, {"property": "companyId", "value": 10101010}]}]

无法解析JSON文件，不断收到ValueError：Extra Data

1 个答案: